Generating Feature Vectors from Phonetic Transcriptions in Cross-Linguistic Data Formats

arXiv:2405.04271v1 Announce Type: new
Abstract: When comparing speech sounds across languages, scholars often make use of feature representations of individual sounds in order to determine fine-grained sound similarities. Although binary feature systems for large numbers of speech sounds have been proposed, large-scale computational applications often face the challenges that the proposed feature systems -- even if they list features for several thousand sounds -- only cover a smaller part of the numerous speech sounds reflected in actual cross-linguistic data. In …

abstract applications arxiv binary challenges computational cs.cl data face feature fine-grained languages numbers scale scholars sound speech systems type vectors